Erkang Cheng
9 papers · 2014–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Half
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Computer Vision
(7)
Domain-Specific
(7)
Analysis
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Machine Learning
(2)
Knowledge & Reasoning
(1)
Architectures
(1)
Learning Types
(1)
Models
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Processing
(1)
Reasoning
(1)
Keywords
autonomous driving
(4)
trajectory prediction
(2)
semi-supervised learning
(1)
low-rank approximation
(1)
depth estimation
(1)
end-to-end learning
(1)
medical image segmentation
(1)
closed-loop evaluation
(1)
transformer encoder
(1)
3d object detection
(1)
diffusion model
(1)
consistency regularization
(1)
bird's eye view
(1)
pseudo label
(1)
medical imaging
(1)
deformable attention
(1)
trajectory planning
(1)
feature perturbation
(1)
semantic segmentation
(1)
motion planning
(1)
Papers
DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving
AAAI 2026
TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relations
CVPR 2026
Cross Image Feature Perturbation with Pseudo Label Fusion for Semi-Supervised Medical Image Segmentation
WACV 2025
Edge-Aware Token Halting for Efficient and Accurate Medical Image Segmentation
MICCAI 2025
HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder
ICCV 2025
Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors
CVPR 2024
SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras
ECCV 2024
BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs
WACV 2023
Curvilinear Structure Tracking by Low Rank Tensor Approximation with Model Propagation
CVPR 2014